abideen commited on
Commit
0ea5b1d
1 Parent(s): ed152d8

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - llama-3-8b
4
+ - sft
5
+ - medical
6
+ base_model:
7
+ - meta-llama/Meta-Llama-3-8B
8
+ license: cc-by-nc-nd-4.0
9
+ ---
10
+
11
+ # JSL-Med-Sft-Llama-3-8B
12
+ [<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com)
13
+
14
+
15
+ This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/).
16
+
17
+ This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at [email protected].
18
+
19
+
20
+
21
+ ## 💻 Usage
22
+
23
+ ```python
24
+ !pip install -qU transformers accelerate
25
+
26
+ from transformers import AutoTokenizer
27
+ import transformers
28
+ import torch
29
+
30
+ model = "johnsnowlabs/JSL-Med-Sft-Llama-3-8B"
31
+ messages = [{"role": "user", "content": "What is a large language model?"}]
32
+
33
+ tokenizer = AutoTokenizer.from_pretrained(model)
34
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
35
+ pipeline = transformers.pipeline(
36
+ "text-generation",
37
+ model=model,
38
+ torch_dtype=torch.float16,
39
+ device_map="auto",
40
+ )
41
+
42
+ outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
43
+ print(outputs[0]["generated_text"])
44
+ ```
45
+ ## 🏆 Evaluation
46
+
47
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
48
+ |-------------------------------|-------|------|-----:|--------|-----:|---|-----:|
49
+ |stem |N/A |none | 0|acc_norm|0.5803|± |0.0067|
50
+ | | |none | 0|acc |0.6141|± |0.0057|
51
+ | - medmcqa |Yaml |none | 0|acc |0.5752|± |0.0076|
52
+ | | |none | 0|acc_norm|0.5752|± |0.0076|
53
+ | - medqa_4options |Yaml |none | 0|acc |0.5970|± |0.0138|
54
+ | | |none | 0|acc_norm|0.5970|± |0.0138|
55
+ | - anatomy (mmlu) | 0|none | 0|acc |0.6963|± |0.0397|
56
+ | - clinical_knowledge (mmlu) | 0|none | 0|acc |0.7472|± |0.0267|
57
+ | - college_biology (mmlu) | 0|none | 0|acc |0.7847|± |0.0344|
58
+ | - college_medicine (mmlu) | 0|none | 0|acc |0.6185|± |0.0370|
59
+ | - medical_genetics (mmlu) | 0|none | 0|acc |0.8300|± |0.0378|
60
+ | - professional_medicine (mmlu)| 0|none | 0|acc |0.7022|± |0.0278|
61
+ | - pubmedqa | 1|none | 0|acc |0.7480|± |0.0194|
62
+
63
+ |Groups|Version|Filter|n-shot| Metric |Value | |Stderr|
64
+ |------|-------|------|-----:|--------|-----:|---|-----:|
65
+ |stem |N/A |none | 0|acc_norm|0.5803|± |0.0067|
66
+ | | |none | 0|acc |0.6141|± |0.0057|